Agent Mode

Agent Mode is Deskless’s multi-step coding workflow for tasks that need more context than a single selected block of code.

Start a task

1. Open the relevant project.
2. Open Agent Mode from the AI surface.
3. Describe the outcome, constraints, and files you already know are relevant.
4. Review the proposed plan before continuing.

Good requests name the intended behavior and important constraints without prescribing every line of the solution.

How the agent works

The agent progresses through a controlled loop:

1. Plan: break the goal into a small sequence of checks and edits.
2. Inspect: rank likely files, look for matching symbols, and gather relevant context.
3. Propose: prepare targeted patches instead of silently rewriting the project.
4. Verify: surface suspicious edits, sensitive paths, and configuration risks.
5. Review: group changes by file and risk so you can inspect every hunk.
6. Apply: write only the changes you approve.

Review controls

Approve or reject a whole file when the patch is straightforward, or review individual hunks when you want finer control. Rejected edits are not applied. An empty patch is treated as no change, not as a replacement file.

Resume later

If the app is backgrounded or the review is interrupted, return to the project and reopen the in-progress agent session. Deskless preserves focused task context so you can continue without starting over.

Safety checklist

Before applying a patch:

• inspect every file path and hunk;
• pay extra attention to build, security, credential, and deployment files;
• confirm the patch reflects the current editor buffer;
• run the project’s normal tests or validation after applying; and
• review the final Git diff before committing.

Agent Mode accelerates the work; it does not replace engineering judgment.